Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 12320
    Prev
    Next
    INDEX
    Explanations

    C++ code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     suffer
    -0.08
     denies
    -0.08
    
    -0.08
     suffers
    -0.08
    	is
    -0.08
    Goto
    -0.08
     બને
    -0.08
    inz
    -0.07
    	bytes
    -0.07
    nv
    -0.07
    POSITIVE LOGITS
     dags
    0.08
    ティ
    0.07
    ært
    0.07
     Ett
    0.07
     ESS
    0.07
    협
    0.07
    েয়
    0.07
    _se
    0.07
    タイ
    0.07
     تس
    0.07
    Activations Density 0.000%

    No Known Activations